CNX Software

Rockchip RK1820/RK1828 SO-DIMM and M.2 LLM/VLM AI accelerator modules, devkits, and benchmarks

Rockchip unveiled two RK182X LLM/VLM accelerators at its developer conference last July, namely the RK1820 with 2.5GB RAM for ...
IEEE

FlanEC: Exploring Flan-T5 for Post-ASR Error Correction

Abstract: In this paper, we present an encoder-decoder model leveraging Flan-T5 for post-Automatic Speech Recognition (ASR) Generative Speech Error Correction (GenSEC ...
marktechpost

Google Introduces T5Gemma 2: Encoder Decoder Models with Multimodal Inputs via SigLIP and 128K Context

T5Gemma 2 follows the same adaptation idea introduced in T5Gemma, initialize an encoder-decoder model from a decoder-only checkpoint, then adapt with UL2. In the above figure the research team show ...
Modern Engineering Marvels on MSN

Google Translate’s real-time speech works on any Android headphones

How fast can a conversation cross languages without breaking its rhythm?” That is what Google Translate’s latest update has answered with one giant leap in functionality and performance. Live speech ...
IEEE

Knowledge Probing on Decoder-Only Models in Medical Domain

Language models (LLMs) have become an integral part of numerous applications in the biomedical domain, leveraging their ability to process and generate human-like text [1]. In this study, we focus on ...
Flying

Same Model, Different Plane: Navigating the Quirks of a Flight School Fleet

Aircraft, even of the same model, possess unique quirks and differences (e.g., panel layouts, flap settings, airspeed indicator units, weight limitations) that demand pilot adaptability and specific ...
marktechpost

Cisco Released Cisco Time Series Model: Their First Open-Weights Foundation Model based on Decoder-only Transformer Architecture

Cisco and Splunk have introduced the Cisco Time Series Model, a univariate zero shot time series foundation model designed for observability and security metrics. It is released as an open weight ...